Inactive evaluations
method: Baidu VIS v22018-07-02
Authors: VIS-OCR
Description: An end-to-end text localization and recognition result submitted by Baidu VIS-OCR, the former OCR team at Baidu IDL.
method: FOTS2018-01-22
Authors: Xuebo Liu, Ding Liang, Shi Yan, Dagui Chen, Yu Qiao, Junjie Yan
Description: A unified end-to-end trainable Fast Oriented Text Spotting (FOTS) network for simultaneous detection and recognition, sharing computation and visual information among the two complementary tasks.
method: SRC-B-MachineLearningLab2018-03-28
Authors: Xiaobing Wang, Yingying Jiang, Xiangyu Zhu, Yi Yu, Haiyang Guo, Hao Guo, Ning An, Zhenbo Luo
Description: Samsung R&D Institute of China - Beijing, Machine Learning Lab.
Detection is based on R2CNN.
Recognition is CNN-LSTM based method.
Description Paper Source Code
| Date | Method | Recall | Precision | Hmean | |||
|---|---|---|---|---|---|---|---|
| 2018-07-02 | Baidu VIS v2 | 80.90% | 88.29% | 84.43% | |||
| 2018-01-22 | FOTS | 73.85% | 93.17% | 82.39% | |||
| 2018-03-28 | SRC-B-MachineLearningLab | 75.08% | 90.80% | 82.19% | |||
| 2017-07-12 | SRC-B-MachineLearningLab | 67.62% | 83.74% | 74.82% | |||
| 2019-04-11 | e2e-mlt + bug fix | 55.46% | 57.55% | 56.49% | |||
| 2016-03-02 | TextProposals + DictNet | 39.22% | 78.29% | 52.26% | |||
| 2016-04-05 | SRC-B-TextProcessingLab | 39.94% | 73.91% | 51.86% | |||
| 2018-10-25 | e2e-mlt | 49.34% | 54.55% | 51.81% | |||
| 2015-11-09 | Megvii-Image++ | 36.16% | 52.17% | 42.71% | |||
| 2021-05-25 | Char-level PTSD on SynthText | 19.05% | 33.33% | 24.24% | |||
| 2015-04-02 | Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 14.96% | 35.60% | 21.07% | |||
| 2015-04-02 | Deep2Text-MO | 14.61% | 22.08% | 17.58% | |||
| 2015-04-02 | Beam search CUNI (decoding for TextSpotter - spell checked) | 6.28% | 66.49% | 11.48% | |||
| 2015-04-02 | Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |